Presentation 2015-03-13
Automatic Examination Sentence Generation System for Kanji Learning Based on Web Text Retrieval
Jun TAKUMA, Jianwei ZHANG,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Generally people learn Kanji for The Japan Kanji Aptitude Test by using workbooks. However, there are two problems of the volume of question sentences and the cost of workbooks. To solve these problems, we developed a Kanji learning system for automatically generating examination sentences from web texts with web retrieval. After a user specifies the test grade and the number of questions, the system generates examination questions from sentences on the internet. After the user answers the questions automatically generated, the system gives marks and presents the learning results to the user. We conducted user studies on three methods: workbooks on public sale, workbooks on the web and our system. The experimental results show our system is remarkably useful for learning Kanji of Grade 1 at low cost.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Kanji learning system / Web text retrieval / Sentence extraction
Paper # WIT2014-86
Date of Issue

Conference Information
Committee WIT
Conference Date 2015/3/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic Examination Sentence Generation System for Kanji Learning Based on Web Text Retrieval
Sub Title (in English)
Keyword(1) Kanji learning system
Keyword(2) Web text retrieval
Keyword(3) Sentence extraction
1st Author's Name Jun TAKUMA
1st Author's Affiliation Tsukuba University of Technology()
2nd Author's Name Jianwei ZHANG
2nd Author's Affiliation Tsukuba University of Technology
Date 2015-03-13
Paper # WIT2014-86
Volume (vol) vol.114
Number (no) 512
Page pp.pp.-
#Pages 6
Date of Issue